Claude

The council worked. One request went to Claude, Codex and Kimi, they answered independently, and nothing touched the lab without a human approval bound to a hash of the exact plan. It also lived entirely in a terminal, which meant that to approve a run I had to type a run id like hc-20260822-6fbfa5 and then re-type the original 350-character request verbatim, because resume rebuilds the context pack from it. Get one character wrong and you have quietly changed the inputs the agents were judged on. ...

I’m not a programmer, and I’m not trying to be one. But the development of new AI models has let me learn concepts that were once too complicated for me to get on my own. As you know, I use Linux a lot — but I still wanted to properly upskill in the command line. So instead of just following a document and re-typing commands in another terminal window, I thought: why not get Claude to build me an interactive game — a Linux CLI practice terminal — that actually lets me learn and memorise the commands? ...

My study notes live in Obsidian. My agent lives in a terminal. For a month those were two separate worlds: when I wanted Claude to clean up the vault, I drove Claude Code at it from outside — point the CLI at the folder, describe the job, check the result in Obsidian afterwards. Claudian collapses that into one window. It’s an open-source community plugin that embeds Claude Code inside Obsidian as a sidebar — the vault becomes the agent’s working directory, and the agent becomes part of the note-taking app. ...